Getting hits on the block list IMMEDIATLEY. Log to file, might be important later

This commit is contained in:
William Jeynes
2026-02-22 15:42:27 +00:00
parent 2f33338007
commit 4d92f14527
3 changed files with 8 additions and 0 deletions
+1
View File
@@ -11,6 +11,7 @@ Final Dissertation Submission Repository
``` ```
├── run.sh # Bash script to run project elements from one place ├── run.sh # Bash script to run project elements from one place
├── data/ # Holder from project data ├── data/ # Holder from project data
| ├── blocked.jsonl # Web search results blocked by the Iffy list
| ├── claims.json # Retreived claims from dbkf fetcher | ├── claims.json # Retreived claims from dbkf fetcher
| ├── dev-eng.csv | ├── dev-eng.csv
| ├── train-eng.csv # Normalized disinformation claims in CSV format from CLAN | ├── train-eng.csv # Normalized disinformation claims in CSV format from CLAN
+2
View File
@@ -1,5 +1,6 @@
import axios from "axios"; import axios from "axios";
import { checkDisinfo } from "./checkDisinfo"; import { checkDisinfo } from "./checkDisinfo";
import { writeToJSONL } from "../utils/writeToJSONL";
export async function queryScraper(query: string): Promise<string[]> { export async function queryScraper(query: string): Promise<string[]> {
const instance = process.env.SCRAPER_INSTANCE; const instance = process.env.SCRAPER_INSTANCE;
@@ -46,6 +47,7 @@ export async function queryScraper(query: string): Promise<string[]> {
const lines: string[] = context.map((item: any) => { const lines: string[] = context.map((item: any) => {
if (checkDisinfo(item.url)) { if (checkDisinfo(item.url)) {
writeToJSONL("blocked.jsonl", {url: item.url, query: query})
return ""; return "";
} }
+5
View File
@@ -0,0 +1,5 @@
import fs from "fs";
export function writeToJSONL(path: string, line: any) {
fs.appendFileSync(`../data/${path}`, JSON.stringify(line) + "\n", "utf-8");
}